NVIDIA Launches Nemotron 3.5 Bolt: A Compact Open Model for Local AI Agents
NVIDIA has released the Nemotron 3.5 Bolt E4B 4GB, an open small language model optimized for consumer hardware like RTX GPUs and Jetson devices. Designed for local voice assistants, interactive game characters, and robotics, this model requires approximately 4GB of VRAM, enabling developers to build responsive, privacy-focused edge AI applications without relying on cloud infrastructure.
Source: MarkTechPost